Parametric classification of multichannel averaged event-related potentials

Lalit Gupta, Jim Phegley, Dermis L. Molfese

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This paper focuses on the systematic development of a parametric approach for classifying averaged event-related potentials (ERPs) recorded from multiple channels. It is shown that the parameters of the averaged ERP ensemble can be estimated directly from the parameters of the single-trial ensemble, thus, making it possible to design a class of parametric classifiers without having to collect a prohibitively large number of single-trial ERPs. An approach based on random sampling without replacement is developed to generate a large number of averaged ERP ensembles in order to evaluate the performance of a classifier. A two-class ERP classification problem is considered and the parameter estimation methods are applied to independently design a Gaussian likelihood ratio classifier for each channel. A fusion rule is formulated to classify an ERP using the classification results from all the channels. Experiments using real and simulated ERPs are designed to show that, through the approach developed, parametric classifiers can be designed and evaluated even when the number of averaged ERPs does not exceed the dimension of the ERP vector. Additionally, it is shown that the performance of a majority rule fusion classifier is consistently superior to the rule that selects a single best channel.

Original languageEnglish (US)
Pages (from-to)905-911
Number of pages7
JournalIEEE Transactions on Biomedical Engineering
Volume49
Issue number8
DOIs
StatePublished - Jul 30 2002

Fingerprint

Classifiers
Fusion reactions
Parameter estimation
Sampling
Experiments

Keywords

  • Event-related potentials
  • Parameter estimation
  • Parametric classification
  • Signal averaging

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Parametric classification of multichannel averaged event-related potentials. / Gupta, Lalit; Phegley, Jim; Molfese, Dermis L.

In: IEEE Transactions on Biomedical Engineering, Vol. 49, No. 8, 30.07.2002, p. 905-911.

Research output: Contribution to journalArticle

@article{1f21ad077c1c4bdb8a65d0131795c9ae,
title = "Parametric classification of multichannel averaged event-related potentials",
abstract = "This paper focuses on the systematic development of a parametric approach for classifying averaged event-related potentials (ERPs) recorded from multiple channels. It is shown that the parameters of the averaged ERP ensemble can be estimated directly from the parameters of the single-trial ensemble, thus, making it possible to design a class of parametric classifiers without having to collect a prohibitively large number of single-trial ERPs. An approach based on random sampling without replacement is developed to generate a large number of averaged ERP ensembles in order to evaluate the performance of a classifier. A two-class ERP classification problem is considered and the parameter estimation methods are applied to independently design a Gaussian likelihood ratio classifier for each channel. A fusion rule is formulated to classify an ERP using the classification results from all the channels. Experiments using real and simulated ERPs are designed to show that, through the approach developed, parametric classifiers can be designed and evaluated even when the number of averaged ERPs does not exceed the dimension of the ERP vector. Additionally, it is shown that the performance of a majority rule fusion classifier is consistently superior to the rule that selects a single best channel.",
keywords = "Event-related potentials, Parameter estimation, Parametric classification, Signal averaging",
author = "Lalit Gupta and Jim Phegley and Molfese, {Dermis L.}",
year = "2002",
month = "7",
day = "30",
doi = "10.1109/TBME.2002.800787",
language = "English (US)",
volume = "49",
pages = "905--911",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "8",

}

TY - JOUR

T1 - Parametric classification of multichannel averaged event-related potentials

AU - Gupta, Lalit

AU - Phegley, Jim

AU - Molfese, Dermis L.

PY - 2002/7/30

Y1 - 2002/7/30

N2 - This paper focuses on the systematic development of a parametric approach for classifying averaged event-related potentials (ERPs) recorded from multiple channels. It is shown that the parameters of the averaged ERP ensemble can be estimated directly from the parameters of the single-trial ensemble, thus, making it possible to design a class of parametric classifiers without having to collect a prohibitively large number of single-trial ERPs. An approach based on random sampling without replacement is developed to generate a large number of averaged ERP ensembles in order to evaluate the performance of a classifier. A two-class ERP classification problem is considered and the parameter estimation methods are applied to independently design a Gaussian likelihood ratio classifier for each channel. A fusion rule is formulated to classify an ERP using the classification results from all the channels. Experiments using real and simulated ERPs are designed to show that, through the approach developed, parametric classifiers can be designed and evaluated even when the number of averaged ERPs does not exceed the dimension of the ERP vector. Additionally, it is shown that the performance of a majority rule fusion classifier is consistently superior to the rule that selects a single best channel.

AB - This paper focuses on the systematic development of a parametric approach for classifying averaged event-related potentials (ERPs) recorded from multiple channels. It is shown that the parameters of the averaged ERP ensemble can be estimated directly from the parameters of the single-trial ensemble, thus, making it possible to design a class of parametric classifiers without having to collect a prohibitively large number of single-trial ERPs. An approach based on random sampling without replacement is developed to generate a large number of averaged ERP ensembles in order to evaluate the performance of a classifier. A two-class ERP classification problem is considered and the parameter estimation methods are applied to independently design a Gaussian likelihood ratio classifier for each channel. A fusion rule is formulated to classify an ERP using the classification results from all the channels. Experiments using real and simulated ERPs are designed to show that, through the approach developed, parametric classifiers can be designed and evaluated even when the number of averaged ERPs does not exceed the dimension of the ERP vector. Additionally, it is shown that the performance of a majority rule fusion classifier is consistently superior to the rule that selects a single best channel.

KW - Event-related potentials

KW - Parameter estimation

KW - Parametric classification

KW - Signal averaging

UR - http://www.scopus.com/inward/record.url?scp=0036077162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036077162&partnerID=8YFLogxK

U2 - 10.1109/TBME.2002.800787

DO - 10.1109/TBME.2002.800787

M3 - Article

C2 - 12148829

AN - SCOPUS:0036077162

VL - 49

SP - 905

EP - 911

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 8

ER -